How to do semantic document similarity using BERT

STEP1:Collect documents and put in a list.

STEP2: Get embedding for each of the documents using BERT. STEP2: Get embedding for each of the documents using BERT.

STEP3: Calculate cosine similarity score between two embeddings STEP3: Calculate cosine similarity score between two embeddings

STEP4: Two documents are similar if their cosine similarities score is high. Follow the link to learn more and code. STEP4: Two documents are similar if their cosine similarities score is high. Follow the link to learn more and code.